.png){kind=icon}
.png){kind=icon}
Return
Steelmaking-continuous casting cycle time prediction method based on industrial data characteristics and model interpretability
.png){kind=icon}
PRE
AI
B
Y
S
H
Q
Z
T
DOI：10.1016/j.cie.2025.111761.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A framework of cycle time prediction for steelmaking production is proposed. • Synthesize features to capture spatiotemporal interaction effects between features. • Permutation importance is applied to reduce redundancy in high-dimensional features. • DNN-SHAP is used to interpret anomaly detection analysis and production optimization. • The proposed prediction method achieves an R2 of 90.1% showing superior performance.
Journal
IF:
6.5
Papers:
1.0W
Citations:
3.8W
Organization
Cited Papers